Enhancing into the Codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders

Audio codecs based on discretized neural autoencoders have recently been developed and shown to provide significantly higher compression levels for comparable quality speech out-put. However, these models are tightly coupled with speech content, and produce unintended outputs in noisy conditions. Ba...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 711 - 715
Main Authors: Casebeer, Jonah, Vale, Vinjai, Isik, Umut, Valin, Jean-Marc, Giri, Ritwik, Krishnaswamy, Arvindh
Format: Conference Proceeding
Language:English
Published: IEEE 06.06.2021
Subjects:
audio compression
Codecs
Convolution
Convolutional codes
Decoding
Speech coding
Speech enhancement
Training
ISSN:2379-190X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Audio codecs based on discretized neural autoencoders have recently been developed and shown to provide significantly higher compression levels for comparable quality speech out-put. However, these models are tightly coupled with speech content, and produce unintended outputs in noisy conditions. Based on VQ-VAE autoencoders with WaveRNN decoders, we develop compressor-enhancer encoders and accompanying decoders, and show that they operate well in noisy conditions. We also observe that a compressor-enhancer model performs better on clean speech inputs than a compressor model trained only on clean speech.
ISSN:2379-190X
DOI:10.1109/ICASSP39728.2021.9414605